import os from pyspark.sql import SparkSession spark = SparkSession.builder.appName("sg-jdbc-read").getOrCreate() spark.sparkContext.setLogLevel("ERROR") orders = spark.read.jdbc( url=os.environ["JDBC_URL"], table="(SELECT order_id, customer_id, total FROM public.orders) AS orders", properties={ "user": os.environ["JDBC_USER"], "password": os.environ["JDBC_PASSWORD"], "driver": "org.postgresql.Driver", }, ) orders.printSchema() print(f"rows={orders.count()}") orders.orderBy("order_id").show(5, truncate=False) spark.stop()